.exe
py main.py
. Install dependencies as needed.To Use the OCR Tool:
First, install Google's Tesseract OCR model here.
This app uses pytesseract; more info can be found here.
Set up your system's environmental variables as necessary.
By default, the software is installed in C:\Program Files\Tesseract-OCR\tesseract.exe
if you're running Windows.
Install the languages you want supported for detection from https://github.com/tesseract-ocr/tessdata
When using the OCR, every screenshot you process is automatically injected into the chat. This works great for translating using your Ollama model. Hit clear to prevent the OCR text from being injected.
When detecting languages, initially it will take several seconds depending on how many languages you have loaded. Once language is detected change the drop down menu to the language your will be using the OCR on for faster recognition.
Starting the Ollama Server:
main.py
.Currently, I don't have an updated .exe
for this due to the OCR binary complications. The .exe
available in the release works; it just lacks newer updated functionalities such as OCR and notes. Also for now this is only meant for Windows